Start the transparent proxy listener. Receives iptables-redirected traffic (no CONNECT tunnels). Shares the same CA cert, rules, and traffic buffer as the explicit proxy. The explicit proxy must be started first.
AI agents invoke proxy_start_transparent to trigger actions in Proxy. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool operates a MITM proxy that intercepts and modifies network traffic at the kernel level via iptables redirection. While it doesn't directly read, write, or delete data, it executes system-level network interception operations that alter traffic flow across applications and devices.
From the tool's definition 'Start the transparent proxy listener' that 'Receives iptables-redirected traffic' and manages 'traffic buffer' — this tool configures and activates network interception infrastructure that redirects and processes system-level traffic, which is a triggering…
Documented attack patterns abuse exactly the kind of access proxy_start_transparent gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Proxy, and nothing reaches the server without passing your rules. This is the rule we recommend for proxy_start_transparent:
{
"version": "1",
"default": "deny",
"tools": {
"proxy_start_transparent": {
"limits": [
{
"counter": "proxy_start_transparent_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}proxy_start_transparent stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Start the transparent proxy listener. Receives iptables-redirected traffic (no CONNECT tunnels). Shares the same CA cert, rules, and traffic buffer as the explicit proxy. The explicit proxy must be started first. It is categorised as a Execute tool in the Proxy MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Proxy MCP server in PolicyLayer and add a rule for proxy_start_transparent: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Proxy. Nothing to install.
proxy_start_transparent is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the proxy_start_transparent rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for proxy_start_transparent. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
proxy_start_transparent is provided by the Proxy MCP server (yfe404/proxy-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Proxy, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
89 Proxy tools catalogued and risk-classified — across an index of 43,000+ MCP servers.